INDEX

Explanations

references to success and achievement

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ingham

-0.17

agon

-0.17

unes

-0.16

imit

-0.15

Zw

-0.14

iqu

-0.14

ado

-0.14

POSITIVE LOGITS

.scalablytyped

0.18

strup

0.15

}):

0.15

enos

0.15

abbo

0.14

aub

0.14

 Geile

0.14

etten

0.14

egov

0.14

_skin

0.14

Activations Density 0.069%

references to success and achievement

No Comments

No Known Activations